Techniques

Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads OSDI 2021 Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference ICML 2021 DPFPS: Dynamic and Progressive Filter Pruning for Compressing Convolutional Neural Networks from Scratch AAAI 2021 DPOQ: Dynamic Precision Onion Quantization ACML 2021 DrNAS: Dirichlet Neural Architecture Search ICLR 2021 Dropout: Explicit Forms and Capacity Control ICML 2021 Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation Interspeech 2021 Dual Attention Guided Gaze Target Detection in the Wild CVPR 2021 DualSANet: Dual Spatial Attention Network for Iris Recognition WACV 2021 Dual Sparse Attention Network For Session-based Recommendation AAAI 2021 Dual-Stream Fusion Network for Spatiotemporal Video Super-Resolution WACV 2021 DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling EMNLP 2021 Dynamic Game Theoretic Neural Optimizer ICML 2021 Dynamic Head: Unifying Object Detection Heads With Attentions CVPR 2021 Dynamic Inference with Neural Interpreters NeurIPS 2021 Dynamic Memory based Attention Network for Sequential Recommendation AAAI 2021 Dynamic Network Quantization for Efficient Video Inference ICCV 2021 Dynamic Normalization and Relay for Video Action Recognition NeurIPS 2021 Dynamic Resolution Network NeurIPS 2021 Dynamic Routing Networks WACV 2021 Dynamic Slimmable Network CVPR 2021 DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network Compilation ICLR 2021 Early Convolutions Help Transformers See Better NeurIPS 2021 Early Stopping in Deep Networks: Double Descent and How to Eliminate it ICLR 2021 ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning EMNLP 2021